© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7461
    Prev
    Next
    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJĮåŁİ
    -0.30
    icals
    -0.27
    heimer
    -0.26
    vation
    -0.26
    nP
    -0.26
     INCIDENTAL
    -0.25
    æ±°
    -0.25
    acb
    -0.25
    ä»ĺè´¹
    -0.24
    ĺ认
    -0.24
    POSITIVE LOGITS
    _bal
    0.29
    енн
    0.25
    _frag
    0.24
     balanced
    0.24
     Pan
    0.24
    å°½åı¯èĥ½
    0.24
     hail
    0.24
     Painting
    0.24
     size
    0.23
     каждой
    0.23
    Activations Density 0.034%

    No Known Activations